Downloads · 30 days
0
gliner-datause-displacement-probe
rafmacalaba/gliner-datause-displacement-probe
gliner-datause-displacement-probe is a token classification model from rafmacalaba. Use it when you need labels on individual words, such as names. It is set up for gliner. The card lists the license as apache-2.0.
Frozen-encoder probe of rafmacalaba/gliner-datause-displacement. The binary DATAMENTION fine-tune absorbed the Luna v2.3 keep/drop boundary into the encoder embeddings; a small MLP head on [start; end; mean; ±64-token…
Access
Public
Updated Sep 4, 2026
Repo size
15.8 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.4 MB · 90%
At a glance
- Task
- Token Classification
- Library
- gliner
- License
- apache-2.0
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 4, 2026
- SHA
- 179be8be
Try a prompt
Model card
From the Hugging Face model README
gliner-datause-displacement-probe
Frozen-encoder probe of rafmacalaba/gliner-datause-displacement. The binary DATA_MENTION fine-tune
absorbed the Luna v2.3 keep/drop boundary into the encoder embeddings; a small
MLP head on [start; end; mean; ±64-token window] span features reads it off the frozen
representation.
Results (holdout)
- head AUROC: 0.7838
- boundary-only 190: head AUROC 0.6659 · best-F1 thr 0.3: prec 0.7500 · rec 0.3429 · f1 0.4706
- raw GLiNER score AUROC: 0.4299
- raw GLiNER score AUROC: 0.4299
- best-F1 thr 0.3: precision 0.7828 · recall 0.7559 · f1 0.7691
- residual-leak diagnostic: 13 high-confidence raw-score FPs, head expelled 6 (46.2%)
Labels come from the Luna v2.3 review (probe_reviewed config of
rafmacalaba/datause-displacement-reviewed); holdout includes the 190
annotator-labelled spans. Head: head.pt; per-span predictions:
holdout_predictions.jsonl.
- Task
- Token Classification
- Library
- gliner
- License
- apache-2.0
- Created
- Sep 3, 2026
- Updated
- Sep 4, 2026